Merge branch 'development'

# Conflicts: # README.md # databases/geneset_generation.R # setup.sh
AG-Boerries · Jul 10, 2020 · 183fe76 · 183fe76
2 parents a80449b + 5df0350
commit 183fe76
Show file tree

Hide file tree

Showing 3 changed files with 18 additions and 7 deletions.
diff --git a/README.md b/README.md
@@ -17,7 +17,7 @@ Prior running the setup script, some components need to be installed manually:
 
 - databases
   - [hallmark gene-sets](http://software.broadinstitute.org/gsea/msigdb/)
-    - h.all.v7.1.entrez.gmt, (any other version should work as well if the filename is adjusted in [geneset_generation.R](https://github.com/AG-Boerries/MIRACUM-Pipe-docker/blob/master/databases/geneset_generation.R) in line 2
+    - h.all.vX.X.entrez.gmt (current release is v7.1 (June 2020))
   - [condel score](https://bbglab.irbbarcelona.org/fannsdb/)
     - fannsdb.tsv.gz
     - fannsdb.tsv.gz.tbi
@@ -34,7 +34,7 @@ To install the databases follow the links, register and download the listed file
 Next, run the setup script. We recommend to install everything, which does **not** include the example and reference data. There are also options to install and setup parts:
 
 ```bash
-./setup.sh -t all
+./setup.sh -t all -m h.all.v.7.1.entrez.gmt
 ```
 
 See `setup.sh -h` to list the available options. By default, we do not install the reference genome as well as our example. If you want to install it run
@@ -51,7 +51,7 @@ See `setup.sh -h` to list the available options. By default, we do not install t
   - create a database for the latest COSMIC release (according to the [annovar manual](http://annovar.openbioinformatics.org/en/latest/user-guide/filter/#cosmic-annotations))
     - Download [prepare_annovar_user.pl](http://www.openbioinformatics.org/annovar/download/prepare_annovar_user.pl) and add to annovar folder
   - register at [COSMIC](https://cancer.sanger.ac.uk/cosmic);
-    - Download the latest release for GRCh37 (as of October 2019 the latest release is v90):
+    - Download the latest release for GRCh37 (as of June 2020 the latest release is v91):
       - VCF/CosmicCodingMuts.vcf.gz
       - VCF/CosmicNonCodingVariants.vcf.gz
       - CosmicMutantExport.tsv.gz

diff --git a/databases/geneset_generation.R b/databases/geneset_generation.R
@@ -1,5 +1,8 @@
 library(GSA)
-gmt <- GSA.read.gmt('h.all.v7.1.entrez.gmt')
+
+args <- commandArgs(trailingOnly = TRUE)
+hallmarks <- args[1]
+gmt <- GSA.read.gmt(hallmarks)
 genesets <- gmt$genesets
 names <- data.frame(Names = gmt$geneset.names, Descriptions = gmt$geneset.descriptions)
 names(genesets) <- names$Names

diff --git a/setup.sh b/setup.sh
@@ -13,13 +13,15 @@ function usage() {
   echo "usage: setup -t task"
   echo "  -t  task            specify task: $(join_by ' ' ${VALID_TASKS})"
   echo "  -h                  show this help screen"
+  echo "  -m  file            MSigDB hallmarks gene-set h.all.vX.X.entrez.gmt file"
   exit 1
 }
 
-while getopts d:t:ph option; do
+while getopts d:t:m:ph option; do
   case "${option}" in
   d) readonly PARAM_DIR_PATIENT=$OPTARG ;;
   t) PARAM_TASK=$OPTARG ;;
+  m) readonly HALLMARKS=$OPTARG ;;
   h) usage ;;
   \?)
     echo "Unknown option: -$OPTARG" >&2
@@ -214,6 +216,12 @@ function install_databases() {
 function setup_databases() {
   echo "setup databases"
 
+  if [[ -z "${HALLMARKS}" ]]; then
+    echo "no hallmarks file provided! Please provide the h.all.vX.X.entrez.gmt file from MSigDB."
+    exit 1
+  fi
+  echo "${HALLMARK}"
+
   cd "${DIR_DATABASES}" || exit 1
 
   BIN_RSCRIPT=$(which Rscript)
@@ -223,9 +231,9 @@ function setup_databases() {
   fi
 
   ## R Code for processing
-  ${BIN_RSCRIPT} --vanilla geneset_generation.R
+  ${BIN_RSCRIPT} --vanilla geneset_generation.R "${HALLMARKS}"
 
-  rm -f h.all.v7.1.entrez.gmt
+  #rm -f "${HALLMARKS}"
 
   echo "done"
 }